{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Z4CNLNQEJV7DZX3W4RBEGNCCBI","short_pith_number":"pith:Z4CNLNQE","canonical_record":{"source":{"id":"2203.04439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-03-08T23:09:25Z","cross_cats_sorted":[],"title_canon_sha256":"0e60c422d267290c15c201d3ade9475fcaf6b6dde96a3e111fd2fe3f0c00da8c","abstract_canon_sha256":"4b4f66e08b541418d0826cb048b4cf8706ab012d110f7efd62891179191dcb54"},"schema_version":"1.0"},"canonical_sha256":"cf04d5b6044d7e3cdf76e4424334420a151625ff04b80bf3c89e6405897f4175","source":{"kind":"arxiv","id":"2203.04439","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.04439","created_at":"2026-07-05T04:03:18Z"},{"alias_kind":"arxiv_version","alias_value":"2203.04439v1","created_at":"2026-07-05T04:03:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.04439","created_at":"2026-07-05T04:03:18Z"},{"alias_kind":"pith_short_12","alias_value":"Z4CNLNQEJV7D","created_at":"2026-07-05T04:03:18Z"},{"alias_kind":"pith_short_16","alias_value":"Z4CNLNQEJV7DZX3W","created_at":"2026-07-05T04:03:18Z"},{"alias_kind":"pith_short_8","alias_value":"Z4CNLNQE","created_at":"2026-07-05T04:03:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Z4CNLNQEJV7DZX3W4RBEGNCCBI","target":"record","payload":{"canonical_record":{"source":{"id":"2203.04439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-03-08T23:09:25Z","cross_cats_sorted":[],"title_canon_sha256":"0e60c422d267290c15c201d3ade9475fcaf6b6dde96a3e111fd2fe3f0c00da8c","abstract_canon_sha256":"4b4f66e08b541418d0826cb048b4cf8706ab012d110f7efd62891179191dcb54"},"schema_version":"1.0"},"canonical_sha256":"cf04d5b6044d7e3cdf76e4424334420a151625ff04b80bf3c89e6405897f4175","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:03:18.391919Z","signature_b64":"uX9bxSL0YAm8uykUqHzZcSyxeYlzEB9Nv4LlniB21DwjX82F1jiC5dzB+uDdnK8Tiy4IoM4q8HsUZR4gcjvyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf04d5b6044d7e3cdf76e4424334420a151625ff04b80bf3c89e6405897f4175","last_reissued_at":"2026-07-05T04:03:18.391581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:03:18.391581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.04439","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:03:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TSWfxgqEzbDyp2pn3/TYrGEMolFLGCX5t1N+meZSW6+DhmIwhm2V+iY3pVluZ1X/VR7rDtZZsMPUQ0i3e9opDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:16:40.495227Z"},"content_sha256":"b4d9f14f389a358cb3ae3627517071303a9e0b501f59fe77b93eb80609c4e3e3","schema_version":"1.0","event_id":"sha256:b4d9f14f389a358cb3ae3627517071303a9e0b501f59fe77b93eb80609c4e3e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Z4CNLNQEJV7DZX3W4RBEGNCCBI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"$\\mathrm{SO}(2)$-Equivariant Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Dian Wang, Robert Platt, Robin Walters","submitted_at":"2022-03-08T23:09:25Z","abstract_excerpt":"Equivariant neural networks enforce symmetry within the structure of their convolutional layers, resulting in a substantial improvement in sample efficiency when learning an equivariant or invariant function. Such models are applicable to robotic manipulation learning which can often be formulated as a rotationally symmetric problem. This paper studies equivariant model architectures in the context of $Q$-learning and actor-critic reinforcement learning. We identify equivariant and invariant characteristics of the optimal $Q$-function and the optimal policy and propose equivariant DQN and SAC "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.04439","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.04439/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:03:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/reTxlsYc8oiTZHB/v8AryZ8gb8E0pGDD9+7xJbMmqyvRKTpw9pyR8atgrj2UmGJl0Li59m516U/6u8MfJukAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:16:40.495911Z"},"content_sha256":"4bc5c01bc63364dd0a1964e8a716c28de2eb5253b4eb63c7b5793e041338f44f","schema_version":"1.0","event_id":"sha256:4bc5c01bc63364dd0a1964e8a716c28de2eb5253b4eb63c7b5793e041338f44f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z4CNLNQEJV7DZX3W4RBEGNCCBI/bundle.json","state_url":"https://pith.science/pith/Z4CNLNQEJV7DZX3W4RBEGNCCBI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z4CNLNQEJV7DZX3W4RBEGNCCBI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T10:16:40Z","links":{"resolver":"https://pith.science/pith/Z4CNLNQEJV7DZX3W4RBEGNCCBI","bundle":"https://pith.science/pith/Z4CNLNQEJV7DZX3W4RBEGNCCBI/bundle.json","state":"https://pith.science/pith/Z4CNLNQEJV7DZX3W4RBEGNCCBI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z4CNLNQEJV7DZX3W4RBEGNCCBI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Z4CNLNQEJV7DZX3W4RBEGNCCBI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4b4f66e08b541418d0826cb048b4cf8706ab012d110f7efd62891179191dcb54","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-03-08T23:09:25Z","title_canon_sha256":"0e60c422d267290c15c201d3ade9475fcaf6b6dde96a3e111fd2fe3f0c00da8c"},"schema_version":"1.0","source":{"id":"2203.04439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.04439","created_at":"2026-07-05T04:03:18Z"},{"alias_kind":"arxiv_version","alias_value":"2203.04439v1","created_at":"2026-07-05T04:03:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.04439","created_at":"2026-07-05T04:03:18Z"},{"alias_kind":"pith_short_12","alias_value":"Z4CNLNQEJV7D","created_at":"2026-07-05T04:03:18Z"},{"alias_kind":"pith_short_16","alias_value":"Z4CNLNQEJV7DZX3W","created_at":"2026-07-05T04:03:18Z"},{"alias_kind":"pith_short_8","alias_value":"Z4CNLNQE","created_at":"2026-07-05T04:03:18Z"}],"graph_snapshots":[{"event_id":"sha256:4bc5c01bc63364dd0a1964e8a716c28de2eb5253b4eb63c7b5793e041338f44f","target":"graph","created_at":"2026-07-05T04:03:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2203.04439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Equivariant neural networks enforce symmetry within the structure of their convolutional layers, resulting in a substantial improvement in sample efficiency when learning an equivariant or invariant function. Such models are applicable to robotic manipulation learning which can often be formulated as a rotationally symmetric problem. This paper studies equivariant model architectures in the context of $Q$-learning and actor-critic reinforcement learning. We identify equivariant and invariant characteristics of the optimal $Q$-function and the optimal policy and propose equivariant DQN and SAC ","authors_text":"Dian Wang, Robert Platt, Robin Walters","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-03-08T23:09:25Z","title":"$\\mathrm{SO}(2)$-Equivariant Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.04439","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b4d9f14f389a358cb3ae3627517071303a9e0b501f59fe77b93eb80609c4e3e3","target":"record","created_at":"2026-07-05T04:03:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4b4f66e08b541418d0826cb048b4cf8706ab012d110f7efd62891179191dcb54","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-03-08T23:09:25Z","title_canon_sha256":"0e60c422d267290c15c201d3ade9475fcaf6b6dde96a3e111fd2fe3f0c00da8c"},"schema_version":"1.0","source":{"id":"2203.04439","kind":"arxiv","version":1}},"canonical_sha256":"cf04d5b6044d7e3cdf76e4424334420a151625ff04b80bf3c89e6405897f4175","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf04d5b6044d7e3cdf76e4424334420a151625ff04b80bf3c89e6405897f4175","first_computed_at":"2026-07-05T04:03:18.391581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:03:18.391581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uX9bxSL0YAm8uykUqHzZcSyxeYlzEB9Nv4LlniB21DwjX82F1jiC5dzB+uDdnK8Tiy4IoM4q8HsUZR4gcjvyCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:03:18.391919Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.04439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4d9f14f389a358cb3ae3627517071303a9e0b501f59fe77b93eb80609c4e3e3","sha256:4bc5c01bc63364dd0a1964e8a716c28de2eb5253b4eb63c7b5793e041338f44f"],"state_sha256":"ab311cf46dbde9d0fcee9d87282d7d3905ffd16d17cdc14c6993222768ab82f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AhuyWPxpNh1Qt8FKm0ad0JADBqC3Ke3yVvfbUgUMK6+zUcozvhHMQUoSv3LhUVvanrDI2MbpLwCCTVYJqxcrDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:16:40.501659Z","bundle_sha256":"4fa404a2a40f48b8619a1ab4759959e312321cf6f9e6e8da87d09860edb1bed5"}}